Parameter-Efficient Transfer Learning for End-to-end Speech Translation

Yunlong Zhao, Kexin Wang, Qianqian Dong, Tom Ko


Abstract
Recently, end-to-end speech translation (ST) has gained significant attention in research, but its progress is hindered by the limited availability of labeled data. To overcome this challenge, leveraging pre-trained models for knowledge transfer in ST has emerged as a promising direction. In this paper, we propose PETL-ST, which investigates parameter-efficient transfer learning for end-to-end speech translation. Our method utilizes two lightweight adaptation techniques, namely prefix and adapter, to modulate Attention and the Feed-Forward Network, respectively, while preserving the capabilities of pre-trained models. We conduct experiments on MuST-C En-De, Es, Fr, Ru datasets to evaluate the performance of our approach. The results demonstrate that PETL-ST outperforms strong baselines, achieving superior translation quality with high parameter efficiency. Moreover, our method exhibits remarkable data efficiency and significantly improves performance in low-resource settings.
Anthology ID:
2024.lrec-main.1102
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
12592–12598
Language:
URL:
https://aclanthology.org/2024.lrec-main.1102
DOI:
Bibkey:
Cite (ACL):
Yunlong Zhao, Kexin Wang, Qianqian Dong, and Tom Ko. 2024. Parameter-Efficient Transfer Learning for End-to-end Speech Translation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12592–12598, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Parameter-Efficient Transfer Learning for End-to-end Speech Translation (Zhao et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.1102.pdf